English
Related papers

Related papers: Size Matters

200 papers

Given large datasets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more efficient to learn them from data? We study empirically how equivariant and…

Machine Learning · Computer Science 2025-07-29 Johann Brehmer , Sönke Behrends , Pim de Haan , Taco Cohen

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

Convolutional neural networks use pooling and other downscaling operations to maintain translational invariance for detection of features, but in their architecture they do not explicitly maintain a representation of the locations of the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Prem Nair , Rohan Doshi , Stefan Keselj

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…

Machine Learning · Computer Science 2015-04-14 Jost Tobias Springenberg , Alexey Dosovitskiy , Thomas Brox , Martin Riedmiller

Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step…

Machine Learning · Computer Science 2019-05-27 Bing Yu , Junzhao Zhang , Zhanxing Zhu

Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance. These architectures only give guarantees for fixed input sizes, yet in…

Machine Learning · Computer Science 2022-10-11 Aaron Zweig , Joan Bruna

The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into…

Machine Learning · Computer Science 2017-08-17 Benjamin J. Lengerich , Sandeep Konam , Eric P. Xing , Stephanie Rosenthal , Manuela Veloso

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 S. H. Shabbeer Basha , Shiv Ram Dubey , Viswanath Pulabaigari , Snehasis Mukherjee

Approximation and learning of classifiers of large data sets by neural networks in terms of high-dimensional geometry and statistical learning theory are investigated. The influence of the VC dimension of sets of input-output functions of…

Machine Learning · Statistics 2025-11-18 Vera Kurkova , Marcello Sanguineti

Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the input. To understand how a network manages to solve a problem…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Pablo Navarrete Michelini , Hanwen Liu , Yunhua Lu , Xingqun Jiang

This paper describes a set of neural network architectures, called Prediction Neural Networks Set (PNNS), based on both fully-connected and convolutional neural networks, for intra image prediction. The choice of neural network for…

Neural and Evolutionary Computing · Computer Science 2019-09-02 Thierry Dumas , Aline Roumy , Christine Guillemot

Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements. The question that naturally arises is what…

Computer Vision and Pattern Recognition · Computer Science 2019-07-26 Cristian Ivan

Current methods for estimating the required neural-network size for a given problem class have focused on methods that can be computationally intensive, such as neural-architecture search and pruning. In contrast, methods that add capacity…

Machine Learning · Computer Science 2023-01-18 Noah Ford , John Winder , Josh McClellan

Our formal understanding of the inductive bias that drives the success of convolutional networks on computer vision tasks is limited. In particular, it is unclear what makes hypotheses spaces born from convolution and pooling operations so…

Neural and Evolutionary Computing · Computer Science 2017-04-19 Nadav Cohen , Amnon Shashua

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant to variations in scale and fail to generalize to objects of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Thomas Altstidl , An Nguyen , Leo Schwinn , Franz Köferl , Christopher Mutschler , Björn Eskofier , Dario Zanca

Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Ken C. L. Wong , Satyananda Kashyap , Mehdi Moradi

Image classification is considered, and a hierarchical max-pooling model with additional local pooling is introduced. Here the additional local pooling enables the hierachical model to combine parts of the image which have a variable…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Benjamin Walter

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Computation and Language · Computer Science 2022-03-21 Houman Mehrafarin , Sara Rajaee , Mohammad Taher Pilehvar

Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of…

Machine Learning · Computer Science 2019-01-31 Babajide O. Ayinde , Tamer Inanc , Jacek M. Zurada